INDEX

Explanations

phrases related to causation

oai_token-act-pair · gpt-3.5-turbo

the word "thereby" and similar phrases indicating causation or consequence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Serge

-0.64

 Atkinson

-0.64

 Freddie

-0.62

cer

-0.61

Kle

-0.61

ten

-0.60

 Kelvin

-0.60

 Columb

-0.60

 Food

-0.60

 Pepper

-0.60

POSITIVE LOGITS

 guiActiveUn

0.99

forth

0.94

hiba

0.84

ãĤ´ãĥ³

0.80

 convol

0.80

 guiActive

0.77

 forfe

0.75

 sidx

0.75

 dwind

0.73

 forfeit

0.73

Activations Density 0.007%

phrases related to causation

the word "thereby" and similar phrases indicating causation or consequence

No Comments

No Known Activations